X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/9f2b33881274af98a9145c533a1d295fad71521a..d1f304bf54caa539923ca447251db0fbda7093c8:/youtube_dl/extractor/common.py?ds=sidebyside diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 14f5756..a692406 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1,3 +1,4 @@ +# coding: utf-8 from __future__ import unicode_literals import base64 @@ -6,6 +7,7 @@ import hashlib import json import netrc import os +import random import re import socket import sys @@ -15,38 +17,56 @@ import math from ..compat import ( compat_cookiejar, compat_cookies, + compat_etree_fromstring, compat_getpass, compat_http_client, + compat_os_name, + compat_str, compat_urllib_error, - compat_urllib_parse, + compat_urllib_parse_unquote, + compat_urllib_parse_urlencode, + compat_urllib_request, compat_urlparse, - compat_str, - compat_etree_fromstring, + compat_xml_parse_error, ) +from ..downloader.f4m import remove_encrypted_media from ..utils import ( NO_DEFAULT, age_restricted, + base_url, bug_reports_message, clean_html, compiled_regex_type, determine_ext, + determine_protocol, error_to_compat_str, ExtractorError, + extract_attributes, fix_xml_ampersands, float_or_none, + GeoRestrictedError, + GeoUtils, int_or_none, + js_to_json, + mimetype2ext, + orderedSet, + parse_codecs, + parse_duration, parse_iso8601, + parse_m3u8_attributes, RegexNotFoundError, - sanitize_filename, sanitized_Request, + sanitize_filename, unescapeHTML, unified_strdate, + unified_timestamp, + update_Request, + update_url_query, + urljoin, url_basename, + xpath_element, xpath_text, xpath_with_ns, - determine_protocol, - parse_duration, - mimetype2ext, ) @@ -77,6 +97,9 @@ class InfoExtractor(object): Potential fields: * url Mandatory. The URL of the video file + * manifest_url + The URL of the manifest file in case of + fragmented media (DASH, hls, hds) * ext Will be calculated from URL if missing * format A human-readable description of the format ("mp4 container with h264/opus"). @@ -104,7 +127,22 @@ class InfoExtractor(object): * protocol The protocol that will be used for the actual download, lower-case. "http", "https", "rtsp", "rtmp", "rtmpe", - "m3u8", or "m3u8_native". + "m3u8", "m3u8_native" or "http_dash_segments". + * fragment_base_url + Base URL for fragments. Each fragment's path + value (if present) will be relative to + this URL. + * fragments A list of fragments of a fragmented media. + Each fragment entry must contain either an url + or a path. If an url is present it should be + considered by a client. Otherwise both path and + fragment_base_url must be present. Here is + the list of all potential fields: + * "url" - fragment's URL + * "path" - fragment's path relative to + fragment_base_url + * "duration" (optional, int or float) + * "filesize" (optional, int) * preference Order number of this format. If this field is present and not None, the formats get sorted by this field, regardless of all other values. @@ -154,20 +192,24 @@ class InfoExtractor(object): * "height" (optional, int) * "resolution" (optional, string "{width}x{height"}, deprecated) + * "filesize" (optional, int) thumbnail: Full URL to a video thumbnail image. description: Full video description. uploader: Full name of the video uploader. - creator: The main artist who created the video. + license: License name the video is licensed under. + creator: The creator of the video. release_date: The date (YYYYMMDD) when the video was released. timestamp: UNIX timestamp of the moment the video became available. upload_date: Video upload date (YYYYMMDD). If not explicitly set, calculated from timestamp. uploader_id: Nickname or id of the video uploader. + uploader_url: Full URL to a personal webpage of the video uploader. location: Physical location where the video was filmed. subtitles: The available subtitles as a dictionary in the format - {language: subformats}. "subformats" is a list sorted from - lower to higher preference, each element is a dictionary - with the "ext" entry and one of: + {tag: subformats}. "tag" is usually a language code, and + "subformats" is a list sorted from lower to higher + preference, each element is a dictionary with the "ext" + entry and one of: * "data": The subtitles file contents * "url": A URL pointing to the subtitles file "ext" will be calculated from URL if missing @@ -204,6 +246,10 @@ class InfoExtractor(object): specified in the URL. end_time: Time in seconds where the reproduction should end, as specified in the URL. + chapters: A list of dictionaries, with the following entries: + * "start_time" - The start time of the chapter in seconds + * "end_time" - The end time of the chapter in seconds + * "title" (optional, string) The following fields should only be used when the video belongs to some logical chapter or section: @@ -213,7 +259,7 @@ class InfoExtractor(object): chapter_id: Id of the chapter the video belongs to, as a unicode string. The following fields should only be used when the video is an episode of some - series or programme: + series, programme or podcast: series: Title of the series or programme the video episode belongs to. season: Title of the season the video episode belongs to. @@ -225,6 +271,24 @@ class InfoExtractor(object): episode_number: Number of the video episode within a season, as an integer. episode_id: Id of the video episode, as a unicode string. + The following fields should only be used when the media is a track or a part of + a music album: + + track: Title of the track. + track_number: Number of the track within an album or a disc, as an integer. + track_id: Id of the track (useful in case of custom indexing, e.g. 6.iii), + as a unicode string. + artist: Artist(s) of the track. + genre: Genre(s) of the track. + album: Title of the album the track belongs to. + album_type: Type of the album (e.g. "Demo", "Full-length", "Split", "Compilation", etc). + album_artist: List of all artists appeared on the album (e.g. + "Ash Borer / Fell Voices" or "Various Artists", useful for splits + and compilations). + disc_number: Number of the disc or other physical medium the track belongs to, + as an integer. + release_year: Year (YYYY) when the album was released. + Unless mentioned otherwise, the fields should be Unicode strings. Unless mentioned otherwise, None is equivalent to absence of information. @@ -266,17 +330,34 @@ class InfoExtractor(object): _real_extract() methods and define a _VALID_URL regexp. Probably, they should also be added to the list of extractors. + _GEO_BYPASS attribute may be set to False in order to disable + geo restriction bypass mechanisms for a particular extractor. + Though it won't disable explicit geo restriction bypass based on + country code provided with geo_bypass_country. (experimental) + + _GEO_COUNTRIES attribute may contain a list of presumably geo unrestricted + countries for this extractor. One of these countries will be used by + geo restriction bypass mechanism right away in order to bypass + geo restriction, of course, if the mechanism is not disabled. (experimental) + + NB: both these geo attributes are experimental and may change in future + or be completely removed. + Finally, the _WORKING attribute should be set to False for broken IEs in order to warn the users and skip the tests. """ _ready = False _downloader = None + _x_forwarded_for_ip = None + _GEO_BYPASS = True + _GEO_COUNTRIES = None _WORKING = True def __init__(self, downloader=None): """Constructor. Receives an optional downloader.""" self._ready = False + self._x_forwarded_for_ip = None self.set_downloader(downloader) @classmethod @@ -296,7 +377,7 @@ class InfoExtractor(object): cls._VALID_URL_RE = re.compile(cls._VALID_URL) m = cls._VALID_URL_RE.match(url) assert m - return m.group('id') + return compat_str(m.group('id')) @classmethod def working(cls): @@ -305,15 +386,59 @@ class InfoExtractor(object): def initialize(self): """Initializes an instance (authentication, etc).""" + self._initialize_geo_bypass(self._GEO_COUNTRIES) if not self._ready: self._real_initialize() self._ready = True + def _initialize_geo_bypass(self, countries): + """ + Initialize geo restriction bypass mechanism. + + This method is used to initialize geo bypass mechanism based on faking + X-Forwarded-For HTTP header. A random country from provided country list + is selected and a random IP belonging to this country is generated. This + IP will be passed as X-Forwarded-For HTTP header in all subsequent + HTTP requests. + + This method will be used for initial geo bypass mechanism initialization + during the instance initialization with _GEO_COUNTRIES. + + You may also manually call it from extractor's code if geo countries + information is not available beforehand (e.g. obtained during + extraction) or due to some another reason. + """ + if not self._x_forwarded_for_ip: + country_code = self._downloader.params.get('geo_bypass_country', None) + # If there is no explicit country for geo bypass specified and + # the extractor is known to be geo restricted let's fake IP + # as X-Forwarded-For right away. + if (not country_code and + self._GEO_BYPASS and + self._downloader.params.get('geo_bypass', True) and + countries): + country_code = random.choice(countries) + if country_code: + self._x_forwarded_for_ip = GeoUtils.random_ipv4(country_code) + if self._downloader.params.get('verbose', False): + self._downloader.to_screen( + '[debug] Using fake IP %s (%s) as X-Forwarded-For.' + % (self._x_forwarded_for_ip, country_code.upper())) + def extract(self, url): """Extracts URL information and returns it in list of dicts.""" try: - self.initialize() - return self._real_extract(url) + for _ in range(2): + try: + self.initialize() + ie_result = self._real_extract(url) + if self._x_forwarded_for_ip: + ie_result['__x_forwarded_for_ip'] = self._x_forwarded_for_ip + return ie_result + except GeoRestrictedError as e: + if self.__maybe_fake_ip_and_retry(e.countries): + continue + raise except ExtractorError: raise except compat_http_client.IncompleteRead as e: @@ -321,6 +446,21 @@ class InfoExtractor(object): except (KeyError, StopIteration) as e: raise ExtractorError('An extractor error has occurred.', cause=e) + def __maybe_fake_ip_and_retry(self, countries): + if (not self._downloader.params.get('geo_bypass_country', None) and + self._GEO_BYPASS and + self._downloader.params.get('geo_bypass', True) and + not self._x_forwarded_for_ip and + countries): + country_code = random.choice(countries) + self._x_forwarded_for_ip = GeoUtils.random_ipv4(country_code) + if self._x_forwarded_for_ip: + self.report_warning( + 'Video is geo restricted. Retrying extraction with fake IP %s (%s) as X-Forwarded-For.' + % (self._x_forwarded_for_ip, country_code.upper())) + return True + return False + def set_downloader(self, downloader): """Sets the downloader for this IE.""" self._downloader = downloader @@ -342,7 +482,7 @@ class InfoExtractor(object): def IE_NAME(self): return compat_str(type(self).__name__[:-2]) - def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True): + def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, data=None, headers={}, query={}): """ Returns the response handle """ if note is None: self.report_download_webpage(video_id) @@ -351,6 +491,14 @@ class InfoExtractor(object): self.to_screen('%s' % (note,)) else: self.to_screen('%s: %s' % (video_id, note)) + if isinstance(url_or_request, compat_urllib_request.Request): + url_or_request = update_Request( + url_or_request, data=data, headers=headers, query=query) + else: + if query: + url_or_request = update_url_query(url_or_request, query) + if data is not None or headers: + url_or_request = sanitized_Request(url_or_request, data, headers) try: return self._downloader.urlopen(url_or_request) except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: @@ -366,13 +514,22 @@ class InfoExtractor(object): self._downloader.report_warning(errmsg) return False - def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True, encoding=None): + def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True, encoding=None, data=None, headers={}, query={}): """ Returns a tuple (page content as string, URL handle) """ # Strip hashes from the URL (#1038) if isinstance(url_or_request, (compat_str, str)): url_or_request = url_or_request.partition('#')[0] - urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal) + # Some sites check X-Forwarded-For HTTP header in order to figure out + # the origin of the client behind proxy. This allows bypassing geo + # restriction by faking this header's value to IP that belongs to some + # geo unrestricted country. We will do so once we encounter any + # geo restriction error. + if self._x_forwarded_for_ip: + if 'X-Forwarded-For' not in headers: + headers['X-Forwarded-For'] = self._x_forwarded_for_ip + + urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal, data=data, headers=headers, query=query) if urlh is False: assert not fatal return False @@ -396,6 +553,34 @@ class InfoExtractor(object): return encoding + def __check_blocked(self, content): + first_block = content[:512] + if ('